Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 25 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.3050. Min Range: -1.3050

Max Act: 1.2828. Min Act: -0.0001

Data Index: 573045 (C4 (Web Text))

Max Activating Token Index: 768

Text #1

Max Range: 1.3050. Min Range: -1.3050

Max Act: 1.3050. Min Act: -0.0001

Data Index: 325707 (C4 (Web Text))

Max Activating Token Index: 597

Text #2

Max Range: 1.3050. Min Range: -1.3050

Max Act: 1.2707. Min Act: -0.0001

Data Index: 1245802 (C4 (Web Text))

Max Activating Token Index: 576

Text #3

Max Range: 1.3050. Min Range: -1.3050

Max Act: 1.2597. Min Act: -0.0001

Data Index: 471079 (C4 (Web Text))

Max Activating Token Index: 800

Text #4

Max Range: 1.3050. Min Range: -1.3050

Max Act: 1.0850. Min Act: -0.0001

Data Index: 352898 (C4 (Web Text))

Max Activating Token Index: 435

Text #5

Max Range: 1.3050. Min Range: -1.3050

Max Act: 1.1860. Min Act: -0.0001

Data Index: 1247954 (C4 (Web Text))

Max Activating Token Index: 435

Text #6

Max Range: 1.3050. Min Range: -1.3050

Max Act: 1.2532. Min Act: -0.0001

Data Index: 499786 (C4 (Web Text))

Max Activating Token Index: 227

Text #7

Max Range: 1.3050. Min Range: -1.3050

Max Act: 1.1342. Min Act: -0.0001

Data Index: 991287 (C4 (Web Text))

Max Activating Token Index: 55

Text #8

Max Range: 1.3050. Min Range: -1.3050

Max Act: 1.1206. Min Act: -0.0001

Data Index: 1118703 (C4 (Web Text))

Max Activating Token Index: 788

Text #9

Max Range: 1.3050. Min Range: -1.3050

Max Act: 1.2034. Min Act: -0.0001

Data Index: 946550 (C4 (Web Text))

Max Activating Token Index: 274

Text #10

Max Range: 1.3050. Min Range: -1.3050

Max Act: 1.0389. Min Act: -0.0001

Data Index: 751062 (C4 (Web Text))

Max Activating Token Index: 191

Text #11

Max Range: 1.3050. Min Range: -1.3050

Max Act: 1.0341. Min Act: -0.0001

Data Index: 844278 (C4 (Web Text))

Max Activating Token Index: 781

Text #12

Max Range: 1.3050. Min Range: -1.3050

Max Act: 1.1216. Min Act: -0.0001

Data Index: 193871 (C4 (Web Text))

Max Activating Token Index: 215

Text #13

Max Range: 1.3050. Min Range: -1.3050

Max Act: 1.0302. Min Act: -0.0001

Data Index: 319000 (C4 (Web Text))

Max Activating Token Index: 756

Text #14

Max Range: 1.3050. Min Range: -1.3050

Max Act: 1.0390. Min Act: -0.0001

Data Index: 1298645 (C4 (Web Text))

Max Activating Token Index: 255

Text #15

Max Range: 1.3050. Min Range: -1.3050

Max Act: 1.1149. Min Act: -0.0000

Data Index: 459260 (C4 (Web Text))

Max Activating Token Index: 117

Text #16

Max Range: 1.3050. Min Range: -1.3050

Max Act: 1.1101. Min Act: -0.0001

Data Index: 539064 (C4 (Web Text))

Max Activating Token Index: 86

Text #17

Max Range: 1.3050. Min Range: -1.3050

Max Act: 1.0920. Min Act: -0.0001

Data Index: 145905 (C4 (Web Text))

Max Activating Token Index: 369

Text #18

Max Range: 1.3050. Min Range: -1.3050

Max Act: 1.0473. Min Act: -0.0001

Data Index: 1161478 (C4 (Web Text))

Max Activating Token Index: 71

Text #19

Max Range: 1.3050. Min Range: -1.3050

Max Act: 1.0738. Min Act: -0.0001

Data Index: 899614 (C4 (Web Text))

Max Activating Token Index: 485